Multiagent Approach to Coreference Resolution Based on the Multifactor Similarity in Ontology Population
- Авторы: Garanina N.1, Sidorova E.1, Seryi A.1
-
Учреждения:
- Ershov Institute of Information Systems, Siberian Branch
- Выпуск: Том 44, № 1 (2018)
- Страницы: 23-34
- Раздел: Article
- URL: https://journals.rcsi.science/0361-7688/article/view/176570
- DOI: https://doi.org/10.1134/S0361768818010036
- ID: 176570
Цитировать
Аннотация
The multiagent approach to coreference resolution in the process of extracting information from texts in natural languages for ontology population is described. Special class agents corresponding to ontology classes are defined. They analyze the available information in the corresponding ontology instances. The results of this analysis are used for values to instance attribute, for detecting duplicates and equivalents of instances, for fixing coreferential relations, and for determining the weights of information connections used to resolve ambiguities. Coreferences are resolved taking into account a multifactor similarity measure between extracted objects that combines the semantic, context, positional, and grammar similarity measures. The class agents work within the multiagent approach to text analysis aimed at ontology population.
Об авторах
N. Garanina
Ershov Institute of Information Systems, Siberian Branch
Автор, ответственный за переписку.
Email: garanina@iis.nsk.su
Россия, Novosibirsk, 630090
E. Sidorova
Ershov Institute of Information Systems, Siberian Branch
Email: garanina@iis.nsk.su
Россия, Novosibirsk, 630090
A. Seryi
Ershov Institute of Information Systems, Siberian Branch
Email: garanina@iis.nsk.su
Россия, Novosibirsk, 630090